Digital Horizons

Automate Your Marketing with AI: Content, Reports and Campaigns

• James Walker & Brian Hastings

Share episode

Want to save hours every week on content creation, client reporting and marketing strategy? In this episode of Digital Horizons, James Walker shares how he’s using AI to automate key areas of the business, from generating social media posts to building campaign insights at scale.

Joined by Brian Hastings, they walk through three real-world AI automation projects that are already up and running inside his business.

You’ll discover:

  • How to automate content creation across YouTube, LinkedIn and Instagram
  • A smarter way to deliver reports using Loom videos and AI-written summaries
  • How AI can analyse your past campaigns, competitor data and brand content to recommend what to do next

These are not just ideas. They are working systems built using tools like n8n, ClickUp and custom AI agents. If you’re a business owner or marketer looking to implement AI into your workflow, this is a real-world look at what’s possible right now.

The Digital Horizons Podcast is hosted by:

James Walker - Managing Director WHD
Brian Hastings - Managing Director Nous

Speaker 1:

I guess more powerful is what I'm finding, and maybe it's not. Maybe there's a whole bunch of Zapier that I just don't know about, but this is an ideal social schedule based on performance over the past few months, based on crawling all of your competitive social media pages. We're looking at what's happening in industry, trends and everything else, and then it's going to schedule and publish it to all of our social media.

Speaker 2:

Welcome back to Digital Horizons. This week it's it's an international edition. We've got James in Thailand and I'm here in James's studio. Welcome, james.

Speaker 1:

Thank you. I'm currently in Bangkok. I've been here for, I think, just over a week now. I've sort of set out on a bit of a one-way journey. At the moment, I'm sure we're not going to be returning back home, but really wanting to use this time while I'm away to focus on building and implementing processes within our business and also, I guess, just be able to spend quite a lot of time with my family as well.

Speaker 2:

Yeah, nice one. It sounds amazing. That feeling of freedom, of not having a return date. It sounds very, very cool.

Speaker 1:

I don't think I've ever done it before, so it's. Yeah, it is a bit strange sort of feeling where you're an open-ended trip and I mean it kind of feels like a holiday, but it's also there's a lot of work happening as well while I'm here, which is kind of fun it would feel like you know the guilt you get after being on holidays for a while.

Speaker 2:

At least you're not going to get that guilty feeling because you're still working that's right.

Speaker 1:

I mean I can't. I can't remember last time I even took a holiday when I wasn't working. So, um, it's pretty normal for me. But it means I've got to think about, well, how can I set up and work and I make sure I've got a workspace and trying to structure days as opposed to normally on a holiday. You're trying to fit working amongst the other stuff. This is more fitting the other stuff amongst the work.

Speaker 2:

So a bit of a change in the situation.

Speaker 2:

That's awesome. We know consistency is key when it comes to making content and building an audience, so we're not going to let you, being overseas, get in the way of recording content for Digital Horizon. So we thought this week you've made leaps and bounds in your AI efficiencies and AI automation journey within your business. Let's jump into it. Do you want to take us through a bit of an update? First, about what you've been working on, the one or two scenarios that you're working on and what you've experienced, what it feels like, what challenges you've come up against and how the output actually is working for the business 100%.

Speaker 1:

So I have hired a couple of AI engineers to help us do the implementation, because I started trying to understand and learn it myself and whilst I was getting I guess, getting time to do this, I felt that it was going to take too long to actually come up with a strategy, understand what I'm trying to do and then also try to learn every single thing that I need to implement it. So I've hired two software engineers and we're currently working on three different projects, which I'm super excited about. The first one, which is what I think I touched on last time, is the automation that is going through dropping a folder into a Google Drive, dropping a file into a Google Drive folder, and then it is then rolling out all the assets that we need and even uploading and posting the content for our other YouTube channel, and this is what we're going to be rolling out for Digital Horizons as well.

Speaker 2:

I saw a sneak preview in one of your beachside TikToks. Yeah, it was awesome.

Speaker 1:

I made a decision. I was like, because one of the girls, one of the engineers, she's currently posting on TikTok about her experience going through this as well and I'm like, oh, I'm going to do this as well. She's currently posting on TikTok about her experience going through this as well, and I'm like, oh, I'm going to do this as well. She's posted five times a day, which I can't imagine doing that volume, but I'm trying to be consistent with it and I'm enjoying doing it. It's making me think about creating content.

Speaker 2:

It does make a bit of pressure to get progress before the next TikTok, Otherwise you're like hey, James, here I'm still at the same spot.

Speaker 1:

I was four hours ago, that's right. So what we've done is we're using NAN, which is, I think, if you imagine, zapier, but I guess more powerful, is what I'm finding, and maybe it's not. Maybe there's a whole bunch of Zapier that I just don't know about, but what we've been finding is NAN's been the perfect platform for what we're doing. Now I don't understand every single step of what's going on in here, but basically what we're doing is we're taking the recording and the video file of the podcast and we're uploading it into a Google Drive. So anyone who's listening along this is going to be a bit hard to picture, but check us out on YouTube, but basically we've got a whole bunch of steps that is taking the video, it's downloading it, it's transcribing it and it's getting an understanding as to what the episode's about. From there, this is then going to generate the content, so it's using our AI agent, which is plugged into Claude, and it's then analyzing the data. It's creating the artwork, so it's understanding who's in the episode, and we've got a database of all of our team members' understanding who's in the episode and we've got a database of all of our team members' headshots, because we're in the artwork for the what's Hot in Digital podcast. We've got different team members' pictures and so I need to understand who is the team member that's in the episode and also find and pull that picture and then it creates the artwork based on that. And so then this area here is that whole situation where it's creating Google drive folders and it's setting all up. It's also writing the captions, so it's actually giving us the name of the episode. It's right in the whole description, and then it is sending us a click up task, which then I have to read it and approve it. This section here is really cool.

Speaker 1:

So this wasn't an area that we had put into the initial plan, but lydia had looked at it. She's our AI engineer. She looked at it and said, well, look, if you have changes to it, it has to rerun the whole step again. So instead, what we've now got it set up as within ClickUp in the actual task, if I make edits to the text, it will then just change it in there and then it pushes it through and doesn't have to rerun the whole thing, which is super cool, saving a lot of time there. That's awesome.

Speaker 1:

And then it goes through and then it's going to upload the videos to YouTube, as you can see on here. So it needs to upload it to YouTube because we need the link to the actual episode. And then it's going to schedule and publish it to all of our social media. So then it creates a LinkedIn post, it creates an Instagram story and all that is then linked to the YouTube episode. It's also pushing it to Buzzsprout and so that way it's going into Spotify and Apple Music and all the different podcast places. And then I get an email which is like hey, this has all been done. Here is a link to the post, here's a link to your YouTube episode, here's a link to the Spotify episode and everything at the end of it.

Speaker 2:

And this is all just from dropping a file into a folder. I mean, how fucking cool is that? So that's literally the trigger.

Speaker 1:

The trigger is the new file being saved in there that was what I originally planned it, but it was originally. Basically I am putting into a file and then I'm just filling out a form. So I have a form which is basically, I insert the url to the mp3, I insert the, the URL to the MP4, and that's it. And then I submit the form and then it just does all of these steps.

Speaker 2:

I'm really interested about the controls. You know the proofing stages. You get a click-up task with the copy and the image for the cover. Is it in that click-up task or is it a link to a draft?

Speaker 1:

video. No, the copy is actually in the task. So I I open the task and it's got exactly. It says linkedin caption this is what it is. Youtube caption this is the name of the title of the episode. Everything is written there, and then a link to the artwork which is it's. It's amazing, like it's just so easy. So I just yeah, a task pops up, probably about three, maybe two to three minutes after I've submitted that form with everything done, and then it can basically just hit approve and then it will then schedule it out to the platforms if we're happy with it. Um, if I want to make any changes, it'll just rerun it, that little part of the copy, and then it will push it out to the channels. So it's um, it's mind-blowing how well it worked.

Speaker 2:

My brain immediately races to other processes in my business that are way simpler than that. That would be amazing to automate.

Speaker 1:

I love that and I mean, this was our first one and we've really set the bar high with this, but I guess, when I was thinking about it, it's like this is basically a SaaS right. If you start thinking about these automations, yeah, could become sellable things like you build this ones. And then it could be like, hey, I could set up a quick website, charge people whatever per subscription and then give them access to this and the amount of time like it's really valuable.

Speaker 1:

Yeah, all they need is the form that's right, and then and and connect it into the credentials, into all their different youtube or whatever, which should be able to set up pretty easily as a streamline process. But I guess that's why this whole journey of I think eventually we will be selling AI services but we want to understand from our side what's really valuable, and this here is super valuable for us and I think anybody is creating content. So that's the first one, that one super excited, that one's currently working and we're using that one now. As I said, we and we're using that one now, as I said, we're going to be doing this for Digital Horizons in the near future. The next project we've got two current other projects that we're currently working on at the moment.

Speaker 1:

One is around reporting. So this one's to save time for our account managers. So every month, our team go into the reports and they'll manually record a video going over and talking about what's going on for our clients a review on their report, basically they and talking about what's going on for our clients a review on their report, basically They've got a live dashboard link which is done in Mottograph and the team member will be like all right, cool, hey, this is what's going on. This is some challenges. This is where we've had some good wins. This is what we're doing different this year or this month or whatever, and so it's basically just an overview summary.

Speaker 1:

But when a client's doing multiple services and they've got multiple team members working on the account, each one of those do on a different video, so it's been quite a bit of a time-consuming thing for our account managers to look at it at the end of the month. So they've got to go through all of our client lists and they've got to go pull the links, they've got to do all these kind of things to review it and then they've got to create a summary to send it off to clients. So basically, what we process way quicker. So by the goal will be everyone just adds their links and everything into a Google sheet and then the automation will then pull all that together, draft the emails and put it into a format where our account managers can just review it. It's going to be written in a tone of voice from our account managers and then hit send and then that will be sent off to our clients, as opposed to a manual process and there's another one that I'm going to save hours every month for our team.

Speaker 2:

So when you say written, do they still record the video?

Speaker 1:

Yeah, so the team will still record the videos because the thing that's important. Obviously we don't want to take out any human aspects out which add a lot of value and I think that currently those videos, our clients love it. It's a part where they're getting a good understanding as to what's going on, because a lot of our clients don't really I mean, they're not from a digital marketing background. So by having that Loom video where it's got the person's face in it and they're talking over the report and running through everything that's been going on, I find that's really powerful. So we don't want to remove that. But it's the actual sending and collating of all this information.

Speaker 1:

So the links to the writing a summary to the client and then all of that, that part there when you're looking at, say, over 100 clients.

Speaker 2:

It's a very time consuming part, so we're trying to work out how to make that more streamlined. That's awesome, and knowing that you've managed to do that seemingly much more complex version with the you know building a YouTube caption and a title and posting it to multiple platforms this one seems way more achievable. As long as the files are being saved in the right place and there's some consistency around how everything is uploaded, I'm now of the belief that anything's possible.

Speaker 1:

That's what I'm finding. Every time we start pulling something together, I'm trying to think of the wildest thing that would be like hey, like what do we think is completely impossible? And let's actually put this as a challenge and how can we make it not impossible? And it kind of feels like magic the way that it comes together.

Speaker 1:

I mean this, this thing that we're talking about with the reporting thing, previously with zapier, 90 of it could have been done with zapier, because it would just be looking at fields in a spreadsheet, pulling that information and then pushing it into a next step. So you'd have your trigger as a toggle, so you'd switch, I guess, a change of field with a dropdown and say, yep, this is ready to send, and then it should be able to pull all that information, but it's not going to be able to write the email, and so that's what we needed to do. Yes, what we're going to do is have the transcripts download and then of the team members running through the video and then understand the context of that and then writing a summary that's put into the email and drafting that email, because just putting the links into an email draft isn't going to be powerful enough. I think that it's that next step.

Speaker 1:

Yeah, understanding the context and understanding the content that's happening, which I think is going to allow for, hopefully, our account managers, especially over time, as it gets to understand the way that they write, because it'll be reviewing previous emails. It's just going to add another layer to the efficiency of it.

Speaker 2:

Yeah, well, there's the comfort level there that you're not using a standardized caption that says, hey, really excited to share our video, our Loom video, of the great results we got this month. What if that client is going through the worst quarter of their lives and you're all positive, whereas when you're looking at the captions and summarising it from what the account manager has been saying in the video, then it'll get the tone right on. Look, it's been a challenging month. There's more challenges than wins, but we're going to talk through it in these Loom videos across the multiple channels. That's amazing.

Speaker 1:

It's just, and also the highlights, and then a good dot point. Hey look, you know, you had a win here. You had a win here. This is what's changed month to month and like having that dot point like summary of it so it's easy to get the access information, because the AI will also be reviewing the report, will also be reviewing the report, and so we'll have not just the transcript but it'll also have the PDF report that it's going to be able to analyze as well.

Speaker 2:

So yeah just that.

Speaker 1:

Again, it seems like a simple thing in terms of all right, cool, hey, we're sending reports. How can we upgrade this? But it seems like I feel like the end result is going to be a massive upgrade in terms of what we're doing and a massive time efficiency saver.

Speaker 2:

I was just about to say, with these, the sort of theme of these automations are the AI element is empowering a new step, which is some form of content creation to enrich what, like you said, Zapier could have previously done, which is a order-based automation. Now you can enrich that with a bit of relevant content or a graphic. But also there's some action points that I guess you could have posted to YouTube before with Zapier. You could have posted to the social channels before, but it's that step of writing the stuff. So it is the theme of what you're looking for all areas where you've been limited in making an automation because there need to be some sort of human content creation input into it. Correct, I mean, if we could have, you've been limited in making an automation because there need to be some sort of human content creation input into it correct.

Speaker 1:

I mean, if we we could have you know that if we wanted to write the captions around the door at all exactly, I could have pulled all that information like from it. But it's taking the human elements out of it and doing it at a level which is able to access so much previous data as well. And I think this is the really part important part of it all is that when it's connecting into all the data points and has all that history and has the ability and this is the next one which I'm really excited I'll talk about next but once it's able to understand and pull from multiple data points at the same time, that as a human operator, it is potentially going to be able to outperform far more because it has the ability to analyze the data at a higher level than I think we would be able to do on our own in the amount of time that you'd be able to dedicate to a task like this.

Speaker 2:

Yeah, absolutely different data points, but also the history of. Well, when we saw the spike last month, it was due to email traffic or you know. Just having everything at its fingertips to be able to draw insights or conclusions is going to make it amazing.

Speaker 1:

Yeah, and I guess that's really what builds onto this next one that we're looking at, and what I'm trying to build here is, I guess, if you were to think about, all right, well, I want to have a resource which think about all the except for each of the different clients that you work with. You work with multiple businesses, even our own business. There are monthly reports gone back potentially years of data. There are ongoing campaigns, campaign schedules, new campaigns being launched every month or whatever. There's organic social media posts consistently being posted to all different channels, and then all this is generating data. There's brand guidelines, there's client meetings with transcriptions from notes. There is feedback that's been given on the graphics and on content that's been provided.

Speaker 1:

Imagine if you were able to have all that information in a format that's being pulled into an agent and then you're able to then communicate with this agent and then it's able to provide you with ideas and concepts for upcoming campaigns based on all that information and all that data that is there, and then being able to provide hey look, this upcoming month we need some ideas for some campaigns. So this upcoming month we need some um concepts for social media posts, and imagine it can then access all of that data and then provide you with hey look, this is an ideal social schedule based on performance over the past few months, based on crawling all of your competitive social media pages, also looking at what's happening in industry trends and everything else, and it's able to look at all of these things and then provide an outline in terms of height. This is potentially a really good schedule that could come up over the next 30 days. So not completely eliminating humans and then coming up with all the different ideas for posts, and then, because it's like all right, well, this got really good engagement.

Speaker 1:

Last time we did something like this, let's try something else like this.

Speaker 1:

We then go, yep, cool, love all those.

Speaker 1:

It then creates the content based on tone of voice, based on all the different previous posts and everything like that, and then allows our social media team to really then spend their time on the strategy, and so this is what we're going to be implement.

Speaker 1:

This is the next thing I'm trying to build, and then we're also going to be able to talk to it and say, hey, look, well, you know what has been our best performing post over the last six months, what has been, like you know, been working, what it hasn't, what should we be doing more of when we're coming up to planning out the next quarter of content or planning out the next quarter of campaigns, and so this is something that we're sort of working through at the moment, and it's got to pull a lot of information, so it's been a much slower one, but I think by the next time we catch up, that we should have had a lot of progress in building this, because it's, I think it, that we don't want to just be uploading to gpt, right, like we want to make sure that it's in a closed network, and because there is going to be um, I guess, confidential information within this that we would like to be able to use, but we want to also make sure that it's safe and secure, and so that's another element and layer that we've got to take into consideration here.

Speaker 1:

so I can't wait to get this rolled out, I mean even just from a proofing and auditing check. Like you know, we're going to launch a new campaign. I want every single piece of content that is running through an auditing process. It's like all right, cool. Look at all the meeting notes, look at all the past campaigns, look at everything that we've talked about in the past month. Does it adhere and is it following everything that we wanted to, before it even gets reviewed or even sent to a client to review? Just having even that step in the process, I think it's going to be really powerful too.

Speaker 2:

Yeah, definitely, and I think when you get consistent at capturing or recording meetings and having those notes available for this to review and read, there's going to be fewer and fewer moments for the AI tool or the agent to be lacking the relevant information to be able to judge or audit the campaigns.

Speaker 2:

I think it's really extending on.

Speaker 2:

We've probably all got a taste of what you can do in GPT, but you get quite generic responses without this training or this deeper level of data. This is really empowering it with everything the person running the campaigns should be aware of, but bringing forward all those learnings from last year or six months ago that they fly out of my mind in that moment when I need to think about it. So, yeah, being able to trust that it's dynamically created strategies or recommendations, insights, I'd say, from the specific client data, not just a prompt or a one-off generic prompt yeah, I think it'll be hugely powerful. When I've tried this with projects in ChatGPT, it feels like there's only so much of the documents I upload it really considers. So if you can have some success in trying this in the tools that you're using, it will be a really powerful next step and then you can start to apply it to just about anything. It's not just automating some of the painful tasks, it's actually your co-thinking strategic partner for each client. It's like your brain for the agency.

Speaker 1:

That's it, and I guess what we're not trying to take the human element out of it. We're trying to amplify what we can do and I think that's the most important part of it is that, whilst this can do a lot of the I guess, the research and different things and data analysis we still want to empower our team to be creative thinkers and really use this as a tool to elevate what they're able to produce for our clients, and not to replace at all. It's more about a way to elevate.

Speaker 2:

Well, absolutely, I think the volume of good work that can be produced and the team then become critical of the work it's producing and making sure it's the best it can be. You'll be able to get out more relevant insights to clients and actual data-backed campaign ideas than you have before. This one feels like a bigger beast of a job, but Even as an agency owner, having the learnings remembered in one place so that if a new team member joins and has to be brought up to speed on a client they can ask it questions. They don't have to bother someone else with. When did that last campaign run? Why don't we run one for plumbing but we do for electrical? What are the typical budgets we spent on this? All that stuff can be at their fingertips and that that's it.

Speaker 1:

It's, it's going to be data and I mean, and by incorporating a voice agent into it, they can. They can sit and have a conversation with it. You can have it like with your sexy voice um, one that you tried out there and conversate. Yeah, what's the best campaign is that we could be running for you know, um, for the client.

Speaker 2:

So, um, I don't know, I'm so excited by it. Don't call it no, that's great, but yeah, it's not my, my chat agent. With this one, we tested together, that's right. Just to recap, you've taken us through three of your initial projects. The first one is definitely close to completion, the second one is underway and the third one is your big, hairy, audacious goal, the first one being an automated workflow that grabs a video asset and the audio asset from a podcast and creates the relevant captions for YouTube and social channels to create posts. It also generates a cover image using the photography of the team members that you've saved for it. It creates all of this ready for you to review in ClickUp. Upon your changes. It makes updates or approval. It then goes forward and posts it and then gives you confirmation that everything's been posted.

Speaker 2:

Streamlining multiple steps and a couple of hours of work for someone. Streamlining multiple steps and a couple of hours of work for someone. The second one was streamlining of the collation of the Loom videos that you use for reporting and also the links to those reports, combining those assets into an email and writing a contextual summary of what the reports include and in the relevant tone of the account manager, and then sending it on to the client for 100 clients. And then the third one is a thought partner for your strategist to understand everything about each individual client, what they've run in their campaigns in the past, their competitor performance, and make suggestions, insights or supporting recommendations for posts, content, strategies to move forward into the next month and work with your internal team members to provide insights back to your clients and recommendations of what to do next, but also even write the stuff for them to review Pretty big stuff. I can't wait to see what happens and I'll probably be buying off you some of these workflows.

Speaker 1:

Yeah, and that's it. I mean, that's stage two, isn't it? It's like we're going to roll it out, make sure it works, make sure it's valuable for us, and then we'll work out well, how can we then make some money out of it, because obviously a lot of investment going into making these things. So then we'll look at how we can help them monetize this as a service.